Datasets and models for the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity: https://arxiv.org/abs/2310.06452
-
Understanding the Effects of RLHF on LLM Generalisation and Diversity
Paper • 2310.06452 • Published • 2 -
UCL-DARK/sequential-instructions
Viewer • Updated • 533 • 85 • 3 -
UCL-DARK/alpaca-farm-id-test
Viewer • Updated • 1.03k • 10 -
UCL-DARK/openai-tldr-summarisation-preferences
Viewer • Updated • 177k • 54 • 1